Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3168 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0269. Min Act: -0.0003

Data Index: 230660 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0268. Min Act: -0.0003

Data Index: 864098 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0236. Min Act: -0.0003

Data Index: 187270 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1211199 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0234. Min Act: -0.0003

Data Index: 316673 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0245. Min Act: -0.0003

Data Index: 766954 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1217382 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0237. Min Act: -0.0003

Data Index: 27067 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0222. Min Act: -0.0003

Data Index: 874765 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1079774 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1281319 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0237. Min Act: -0.0003

Data Index: 873841 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0211. Min Act: -0.0003

Data Index: 835487 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0212. Min Act: -0.0003

Data Index: 949049 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0212. Min Act: -0.0003

Data Index: 671818 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1335276 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0189. Min Act: -0.0003

Data Index: 745642 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0193. Min Act: -0.0003

Data Index: 154079 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0204. Min Act: -0.0003

Data Index: 154314 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0207. Min Act: -0.0003

Data Index: 465695 (C4 (Web Text))

Max Activating Token Index: 944